Open-AgentRL: RLAnything (ICML 2026) & AutoTool (ICML 2026), DemyAgent: Open-Source RL for LLMs and Agentic Scenarios

by Gen-Verse · Agent Tool · ★ 642

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

How to install Open-AgentRL

git clone https://github.com/Gen-Verse/Open-AgentRL.git

Taken from the project's README on GitHub. Check the security audit before running it.

Security audit verdict: SAFE · quality 65/100

None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.

agent-rlcoding-agententropy-methodgrpogui-agentllm-agentllm-reasoningmulti-agent-reinforcement-learningpporeinforcement-learning

Quick Facts

Stars642
Forks60
LanguagePython
CategoryAgent Tool
LicenseApache-2.0
Quality Score65/100
Open Issues12
Last Updated2026-06-12
Created2025-10-13
Platformspython
Est. Tokens~13k

About Open-AgentRL

RLAnything (ICML 2026) & AutoTool (ICML 2026), DemyAgent: Open-Source RL for LLMs and Agentic Scenarios RLAnything (click to expand) RLAnything: Forge Environment, Policy, and Reward Model in Completely Dynamic RL System An overview of our research on RLAnything. In this work, we propose RLAnything, a reinforcement learning framework that dynamically optimizes each component through close

Compatible Skills

These tools work well together with Open-AgentRL for enhanced workflows:

  • MetaClaw — semantic(0.28)+complementary+rare_topics+same_lang+similar_pop+shared_platform (59%)
  • OpenJudge — semantic(0.17)+complementary+rare_topics+same_lang+similar_pop+shared_platform (56%)
  • AWorld — semantic(0.27)+complementary+same_lang+similar_pop+shared_platform (54%)
  • LiteMultiAgent — semantic(0.25)+complementary+same_lang+similar_pop+shared_platform (54%)
  • SecGPT — semantic(0.22)+complementary+same_lang+similar_pop+shared_platform (53%)

Open-AgentRL alternative? Top 6 similar tools

Looking for a Open-AgentRL alternative? If you're comparing Open-AgentRL with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • llm-rl-environments-lil-course by anakin87 · ⭐ 235

    🌱 A little course on Reinforcement Learning Environments for evaluating and training Language Models

  • NEWTON by CUTEPKQ · ⭐ 143

    NEWTON: Agentic Planning for Physically Grounded Video Generation

  • ICLR2025-Papers-with-Code by yinizhilian · ⭐ 589

    历年ICLR论文和开源项目合集，包含ICLR2021、ICLR2022、ICLR2023、ICLR2024、ICLR2025.

  • reevo by ai4co · ⭐ 303

    [NeurIPS 2024] ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution

  • unsloth-buddy by TYH-labs · ⭐ 280

    Zero-friction LLM fine-tuning skill for Claude Code, Gemini CLI & any ACP agent. Unsloth on NVIDIA · TRL+MPS/M

  • Awesome-LLM-Reasoning-with-NeSy by LAMDASZ-ML · ⭐ 271

    ✨✨Latest Advances on Neuro-Symbolic Learning in the era of Large Language Models

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Python Agent Tools

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Agent Tool tools